Abstract | ||
---|---|---|
In this paper two types of redundancy analysis, one based on linear redundancy and the other based on nonlinear entropy-based redundancy, are applied to the OTAGO speech corpus in order to classify the phonemes according to their nonlinearity properties. The redundancy curves are compared both in qualitative as well as in quantitative manner, the latter way involving the generation of two kinds of surrogate data. The results indicate the existence of trivial and dynamic nonlinearities in certain phonemes. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1016/j.csl.2007.09.004 | Computer Speech & Language |
Keywords | Field | DocType |
linear redundancy,dynamic nonlinearities,quantitative manner,redundancy,redundancy curve,nonlinear entropy-based redundancy,otago speech corpus,phoneme analysis,nonlinearity property,entropy measurement,qualitative entropy measurement,certain phoneme,redundancy analysis,surrogate data | Speech corpus,Nonlinear system,Computer science,Computational linguistics,Speech recognition,Redundancy (engineering),Artificial intelligence,Natural language processing,Surrogate data,Machine learning | Journal |
Volume | Issue | ISSN |
22 | 4 | Computer Speech & Language |
Citations | PageRank | References |
1 | 0.41 | 16 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jari Turunen | 1 | 52 | 6.63 |
Tarmo Lipping | 2 | 70 | 14.54 |